Deep Network Approximation Characterized by Number of Neurons. Communications in Computational Physics, [S. l.], v. 28, n. 5, p. 1768–1811, 2020. DOI: 10.4208/cicp.OA-2020-0149. Disponível em: https://staging.gsp.tricubic.dev/cicp/article/view/6897. Acesso em: 17 mar. 2026.